Rlaif: Scaling Reinforcement Learning from Human Feedback with AI Feedback (arxiv.org)

1 points by maccaw 2y ago ↗ HN

0 comments

[ 4.5 ms ] story [ 2.3 ms ] thread

No comments yet.

A showcase of shard-db. Data from the Hacker News API. Refreshed every 15 minutes.

Source · Live DB stats